© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6170
    Prev
    Next
    INDEX
    Explanations

    specific terms and structures related to database queries and data schemas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after identifiers like "ID" or "id"

    np_acts-logits-general · gemini-2.0-flash

    variable identifiers and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.80
    addCriterion
    -0.65
     ролях
    -0.63
    WriteBarrier
    -0.62
     للمعارف
    -0.61
    ->___
    -0.60
    Coordonnées
    -0.57
    GIVEREF
    -0.56
     teammate
    -0.55
    MessageState
    -0.55
    POSITIVE LOGITS
    VersionUID
    0.93
    ID
    0.65
    Id
    0.63
    SourceChecksum
    0.57
     ID
    0.55
    id
    0.53
    FXML
    0.51
    type
    0.48
    lucene
    0.47
    名
    0.47
    Activations Density 0.254%

    No Known Activations